vwu.ai Sihai Models

Call and interact with vwu.ai Sihai models including sihai-i2v-31, sihai-image-27, sihai-t2v-29, and sihai-tts-25 with OpenAI-compatible API.

Security Scan

The skill appears to do what it says (call vwu.ai models) but has mismatches and small risky behaviors (undeclared required API key, prints part of the key on error, undeclared binary dependencies) that you should understand before installing.

Purpose & Capability

The skill's name and description (call vwu.ai Sihai models) match the included script and SKILL.md. However the registry metadata lists no required environment variables while SKILL.md and vwu-chat.sh clearly require VWU_API_KEY (and optionally VWU_BASE_URL). This mismatch is an incoherence between declared requirements and actual needs.

Instruction Scope

SKILL.md and the shell script only instruct the agent to call vwu.ai's API and print responses — no broad system access is requested. Caveats: the script prints the first 8 characters of VWU_API_KEY in some error cases (information leakage), and it expects jq and curl (and uses a zsh shebang) though no binaries are declared.

Install Mechanism

No install spec or remote downloads — this is an instruction-only skill with a bundled shell script. No external code is fetched at install-time, which limits supply-chain risk.

Credentials

The skill uses an API key (VWU_API_KEY) and a base URL; those are proportionate to the described purpose. However the skill metadata does not declare the required VWU_API_KEY, and the script reveals the first 8 characters of the key on quota errors. Also it assumes jq/curl availability without declaring them.

Persistence & Privilege

The skill is not always-enabled and does not request elevated or persistent system privileges. It doesn't modify other skills or system-wide settings.

What to consider before installing

This skill appears to implement what it claims (calling vwu.ai models) but has a few issues to consider before installing: - The package metadata claims no required env vars, but SKILL.md and the script require VWU_API_KEY (and may use VWU_BASE_URL). Expect to provide an API key. - The bundled script prints the first 8 characters of your API key on certain API errors — while partial, that is an information leak you may prefer to avoid. Consider editing the script to remove that line before use. - The script uses curl and jq and has a zsh shebang; ensure those binaries are present and that running a zsh script is acceptable in your environment. - The skill's source and homepage are unknown; if you don't trust the owner, verify the script and confirm the vwu.ai endpoint before providing credentials. Recommended actions: ask the publisher to update metadata to declare VWU_API_KEY as a required env var, remove printing of API key fragments, and document binary requirements (curl, jq). If you accept those caveats and trust vwu.ai, the skill is functionally appropriate; otherwise do not install or run without reviewing/modifying the script.

sihai Models for vwu.ai

vwu.ai 平台上的 sihai 模型调用技能。

支持的模型

• sihai-i2v-31
• sihai-image-27
• sihai-t2v-29
• sihai-tts-25

共 4 个模型。

配置

使用前需要设置 vwu.ai API key:

export VWU_API_KEY="your-key-here"

获取 key: https://vwu.ai 控制台

使用示例

# 调用模型
vwu-chat --model sihai-i2v-31 "你的问题"

API 兼容性

所有模型兼容 OpenAI API 格式，支持标准 chat completions 接口。

额度提示

如果使用时提示"额度不足"或类似错误：

1. 访问 https://vwu.ai
2. 在控制台充值或调整额度
3. 或生成新的 API key

---

由 Claw 自动生成 | 源数据: vwu.ai